主题图谱 / audio and speech processing

audio and speech processing

GeneTech 知识引擎共收录 247 篇相关科研实体，横跨 18 个垂直领域。数据来自 OpenAlex、arXiv、Crossref、PubMed、Europe PMC 等公开学术源，全部可溯源到原文。

年度产出趋势

相关主题

代表性文献（按质量分排序，前 60 条）

• Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentation
  2026 · AI 安全与对齐 · The Room Acoustics and Speaker Distance Estimation (SDE) Challenge at ICASSP 2025 explores the effectiveness of augmented room impulse response (RIR) data for improving SDE model performance. This challenge at GenDARA in…
• The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era
  2026 · 量子计算 · Driven by the rapid advancement of Large Language Models (LLMs), particularly Audio-LLMs and Omni-models, spoken dialogue systems have evolved significantly, progressively narrowing the gap between human-machine and huma…
• MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI
  2025 · AI 安全与对齐 · Since 2023, generative AI has rapidly advanced in the music domain. Despite significant technological advancements, music-generative models raise critical ethical challenges, including a lack of transparency and accounta…
• Embedding Alignment in Code Generation for Audio
  2025 · AI 安全与对齐 · LLM-powered code generation has the potential to revolutionize creative coding endeavors, such as live-coding, by enabling users to focus on structural motifs over syntactic details. In such domains, when prompting an LL…
• A Traditional Approach to Symbolic Piano Continuation
  2025 · AI 安全与对齐 · We present a traditional approach to symbolic piano music continuation for the MIREX 2025 Symbolic Music Generation challenge. While computational music generation has recently focused on developing large foundation mode…
• Aligned Better, Listen Better for Audio-Visual Large Language Models
  2025 · AI 安全与对齐 · Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter…
• Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
  2025 · AI 安全与对齐 · We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier…
• More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI
  2025 · AI 安全与对齐 · Longitudinal engagement with generative AI (GenAI) storytelling agents is a timely but less charted domain. We explored multi-generational experiences with "Dreamsmithy," a daily dream-crafting app, where participants (N…
• Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization
  2025 · AI 安全与对齐 · Imagine hearing a dog bark and turning toward the sound only to see a parked car, while the real, silent dog sits elsewhere. Such sensory conflicts test perception, yet humans reliably resolve them by prioritizing sound …
• RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection
  2025 · AI 安全与对齐 · This study introduces RUMAA, a transformer-based framework for music performance analysis that unifies score-to-performance alignment, score-informed transcription, and mistake detection in a near end-to-end manner. Unli…
• A Traditional Approach to Symbolic Piano Continuation
  2025 · 脑科学 · We present a traditional approach to symbolic piano music continuation for the MIREX 2025 Symbolic Music Generation challenge. While computational music generation has recently focused on developing large foundation mode…
• Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training
  2025 · 量子材料 · This report details MERL's system for room impulse response (RIR) estimation submitted to the Generative Data Augmentation Workshop at ICASSP 2025 for Augmenting RIR Data (Task 1) and Improving Speaker Distance Estimatio…
• Speaker- and Text-Independent Estimation of Articulatory Movements and Phoneme Alignments from Speech
  2024 · AI 安全与对齐 · This paper introduces a novel combination of two tasks, previously treated separately: acoustic-to-articulatory speech inversion (AAI) and phoneme-to-articulatory (PTA) motion estimation. We refer to this joint task as a…
• MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers
  2024 · AI 安全与对齐 · Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimo…
• Less Peaky and More Accurate CTC Forced Alignment by Label Priors
  2024 · AI 安全与对齐 · Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), …
• Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition
  2024 · AI 安全与对齐 · Speech emotion recognition (SER) has gained significant attention due to its several application fields, such as mental health, education, and human-computer interaction. However, the accuracy of SER systems is hindered …
• Brilla AI: AI Contestant for the National Science and Maths Quiz
  2024 · AI 驱动科学发现 · The African continent lacks enough qualified teachers which hampers the provision of adequate learning support. An AI could potentially augment the efforts of the limited number of teachers, leading to better learning ou…
• SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
  2024 · 地外矿物 · The rapid advancement of AI-generated singing voices, which now closely mimic natural human singing and align seamlessly with musical scores, has led to heightened concerns for artists and the music industry. Unlike spok…
• The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech
  2024 · 地外矿物 · We present our system (denoted as T05) for the VoiceMOS Challenge (VMC) 2024. Our system was designed for the VMC 2024 Track 1, which focused on the accurate prediction of naturalness mean opinion score (MOS) for high-qu…
• ICASSP 2024 Speech Signal Improvement Challenge
  2024 · 地外矿物 · The ICASSP 2024 Speech Signal Improvement Grand Challenge is intended to stimulate research in the area of improving the speech signal quality in communication systems. This marks our second challenge, building upon the …
• SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
  2024 · 地外矿物 · This paper describes the FBK's participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year's submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which…
• SSDM: Scalable Speech Dysfluency Modeling
  2024 · 地外矿物 · Speech dysfluency modeling is the core module for spoken language learning, and speech therapy. However, there are three challenges. First, current state-of-the-art solutions\cite{lian2023unconstrained-udm, lian-anumanch…
• Towards auditory attention decoding with noise-tagging: A pilot study
  2024 · 仿生智能 · Auditory attention decoding (AAD) aims to extract from brain activity the attended speaker amidst candidate speakers, offering promising applications for neuro-steered hearing devices and brain-computer interfacing. This…
• Imagined Speech State Classification for Robust Brain-Computer Interface
  2024 · 仿生智能 · This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional mac…
• Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
  2024 · 数字孪生 · Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the…
• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks
  2024 · 具身智能 · Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus ac…
• ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data
  2024 · 具身智能 · Audio signals provide rich information for the robot interaction and object properties through contact. This information can surprisingly ease the learning of contact-rich robot manipulation skills, especially when the v…
• SSDM: Scalable Speech Dysfluency Modeling
  2024 · 生命科学 · Speech dysfluency modeling is the core module for spoken language learning, and speech therapy. However, there are three challenges. First, current state-of-the-art solutions\cite{lian2023unconstrained-udm, lian-anumanch…
• Understanding Pedestrian Movement Using Urban Sensing Technologies: The Promise of Audio-based Sensors
  2024 · 低空经济 · While various sensors have been deployed to monitor vehicular flows, sensing pedestrian movement is still nascent. Yet walking is a significant mode of travel in many cities, especially those in Europe, Africa, and Asia.…
• SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
  2024 · 量子计算 · The rapid advancement of AI-generated singing voices, which now closely mimic natural human singing and align seamlessly with musical scores, has led to heightened concerns for artists and the music industry. Unlike spok…
• The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech
  2024 · 量子计算 · We present our system (denoted as T05) for the VoiceMOS Challenge (VMC) 2024. Our system was designed for the VMC 2024 Track 1, which focused on the accurate prediction of naturalness mean opinion score (MOS) for high-qu…
• Towards an AI to Win Ghana's National Science and Maths Quiz
  2023 · AI 驱动科学发现 · Can an AI win Ghana's National Science and Maths Quiz (NSMQ)? That is the question we seek to answer in the NSMQ AI project, an open-source project that is building AI to compete live in the NSMQ and win. The NSMQ is an …
• Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
  2026 · 智慧农业 · With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become highly relevant. We observe that changing the precision of an A…
• How Much AI Is in This Track? Quantifying the Proportion of AI-Generated Stems in Hybrid Music Mixtures
  2026 · AI 安全与对齐 · AI-generated music is increasingly used at the stem level, with producers integrating synthetic drums, basslines, or vocals alongside human-performed instruments. However, current AI music detection systems are binary, t…
• Progressive Alignment Objectives for Aligner-Encoder based ASR
  2026 · AI 安全与对齐 · Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the encoder must learn the alignment internally …
• Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion
  2026 · AI 安全与对齐 · Diffusion and flow matching TTS faces a tension between discrete temporal structure and continuous spectral modeling. Two-stage models diffuse on fixed alignments, often collapsing to mean prosody; single-stage models av…
• LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression
  2026 · AI 安全与对齐 · We propose a lightweight multi-path alignment network (LMPAN) for on-device joint acoustic echo cancellation (AEC) and noise suppression (NS) in full-duplex spoken dialogue systems. To address hardware-induced distortion…
• Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models
  2026 · AI 安全与对齐 · Sound symbolism, the human tendency to map speech sounds to perceptual qualities such as roundness or sharpness, arises primarily from the acoustics of speech rather than spelling. Whether Speech Language Models (SLMs) s…
• Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling
  2026 · AI 安全与对齐 · The rapid progress of large language models (LLMs) has opened up a new frontier for automatic speech recognition (ASR), making their effective integration a critical and challenging research direction. To this end, this …
• Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition
  2026 · AI 安全与对齐 · The emergence of Large Audio-Language Models (LALMs) has advanced Speech Emotion Recognition (SER), but their size limits deployment in resource-constrained environments. While Knowledge Distillation is effective for LAL…
• SGPA: Spectrogram-Guided Phonetic Alignment for Feasible Shapley Value Explanations in Multimodal Large Language Models
  2026 · AI 安全与对齐 · Explaining the behavior of end-to-end audio language models via Shapley value attribution is intractable under native tokenization: a typical utterance yields over $150$ encoder frames, inflating the coalition space by r…
• VeRe-Flow: Guiding Flow Matching toward Clean Speech via Velocity Contrastive Regularization and Representation Alignment for Noise-Robust Bandwidth Expansion
  2026 · AI 安全与对齐 · Noise-robust bandwidth expansion aims to reconstruct high-fidelity wideband speech from noisy low-resolution inputs. While flow matching has shown strong performance in speech generation, accurately recovering clean spee…
• Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
  2026 · AI 安全与对齐 · Significant disparities exist in the diagnosis and clinical presentation of depression across different linguistic populations. Speech-based depression detection performs well monolingually, but cross-lingual generalizat…
• ICASSP 2026 URGENT Speech Enhancement Challenge
  2026 · 量子计算 · The ICASSP 2026 URGENT Challenge advances the series by focusing on universal speech enhancement (SE) systems that handle diverse distortions, domains, and input conditions. This overview paper details the challenge's mo…
• The ICASSP 2026 Automatic Song Aesthetics Evaluation Challenge
  2026 · 量子计算 · This paper summarizes the ICASSP 2026 Automatic Song Aesthetics Evaluation (ASAE) Challenge, which focuses on predicting the subjective aesthetic scores of AI-generated songs. The challenge consists of two tracks: Track …
• The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models
  2026 · 量子计算 · This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders as front-end modules for Large Audio La…
• Language-Invariant Multilingual Speaker Verification for the TidyVoice 2026 Challenge
  2026 · 量子计算 · Multilingual speaker verification (SV) remains challenging due to limited cross-lingual data and language-dependent information in speaker embeddings. This paper presents a language-invariant multilingual SV system for t…
• RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations
  2026 · 量子计算 · RADAR Challenge 2026 is an APSIPA Grand Challenge on Robust Audio Deepfake Recognition under Media Transformations, designed to simulate realistic media conditions in real-world audio distribution pipelines, including co…
• Domain-Agnostic Incremental Learning for Sound Classification. A DCASE 2026 Challenge task
  2026 · 量子计算 · This paper presents the Domain-Agnostic Incremental Learning for Audio Classification Task of the DCASE 2026 Challenge. Incremental learning refers to sequentially learning new tasks with the same system while maintainin…
• VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track
  2026 · 量子计算 · Audio reasoning requires multi-step, evidence-grounded inference over temporally dynamic and acoustically mixed signals, exceeding conventional perception tasks such as ASR or captioning. We present VISA, our submission …
• NLP-Based Review for Toxic Comment Detection Tailored to the Chinese Cyberspace
  2026 · 中医药工具 · With the in-depth integration of mobile Internet and widespread adoption of social platforms, user-generated content in the Chinese cyberspace has witnessed explosive growth. Among this content, the proliferation of toxi…
• Whisper Has an Internal Word Aligner
  2025 · AI 安全与对齐 · There is an increasing interest in obtaining accurate word-level timestamps from strong automatic speech recognizers, in particular Whisper. Existing approaches either require additional training or are simply not compet…
• Improving Stereo 3D Sound Event Localization and Detection: Perceptual Features, Stereo-specific Data Augmentation, and Distance Normalization
  2025 · AI 安全与对齐 · This technical report presents our submission to Task 3 of the DCASE 2025 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. We address the audio-only task in this report and introd…
• Large-Scale Training Data Attribution for Music Generative Models via Unlearning
  2025 · AI 安全与对齐 · This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the m…
• Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation
  2025 · AI 安全与对齐 · This paper describes the synthesis of the room acoustics challenge as a part of the generative data augmentation workshop at ICASSP 2025. The challenge defines a unique generative task that is designed to improve the qua…
• Personality-Enhanced Multimodal Depression Detection in the Elderly
  2025 · AI 安全与对齐 · This paper presents our solution to the Multimodal Personality-aware Depression Detection (MPDD) challenge at ACM MM 2025. We propose a multimodal depression detection model in the Elderly that incorporates personality c…
• Open-Set Source Tracing of Audio Deepfake Systems
  2025 · AI 安全与对齐 · Existing research on source tracing of audio deepfake systems has focused primarily on the closed-set scenario, while studies that evaluate open-set performance are limited to a small number of unseen systems. Due to the…
• T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback
  2025 · AI 安全与对齐 · Text-to-audio (T2A) generation has achieved remarkable progress in generating a variety of audio outputs from language prompts. However, current state-of-the-art T2A models still struggle to satisfy human preferences for…
• Non-native Children's Automatic Speech Assessment Challenge (NOCASA)
  2025 · AI 安全与对齐 · This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to develop new systems that can assess singl…
• Assessing the Alignment of Audio Representations with Timbre Similarity Ratings
  2025 · AI 安全与对齐 · Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of gene…

以 API 获取该主题全量数据

# 主题词表（含本主题的站点分布与年度分布）
curl http://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl http://data.swarmlabs.tools/api/graph.json

需要按主题批量拉取、导出 BibTeX 或接入 AI Agent？查看 数据下载与格式 或 MCP 接入。